AI/amd-strix-halo-vllm-toolboxes
2
0
Fork 0
Code Issues Pull-Requests Actions Pakete Projekte Releases Wiki Aktivität
Dateien
3b0e736c94f78e892f49c232c40760a03d007e8e
amd-strix-halo-vllm-toolboxes/benchmarks/max_context_results.json
T
Donato Capitella 5e8b6bb545 updates
2025-12-20 11:37:06 +00:00

333 Zeilen
7.2 KiB
JSON
Originalformat Blame Verlauf

[
{
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 829952,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tp": 1,
"util": "0.95",
"max_seqs": 4,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 830064,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tp": 1,
"util": "0.95",
"max_seqs": 8,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 830080,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tp": 1,
"util": "0.95",
"max_seqs": 16,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 830064,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "google/gemma-3-12b-it",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 246032,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "google/gemma-3-12b-it",
"tp": 1,
"util": "0.95",
"max_seqs": 4,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 246064,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "google/gemma-3-12b-it",
"tp": 1,
"util": "0.95",
"max_seqs": 8,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 246064,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "google/gemma-3-12b-it",
"tp": 1,
"util": "0.95",
"max_seqs": 16,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 246064,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "Qwen/Qwen3-14B-AWQ",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 40960,
"configured_len": 0,
"real_capacity": 0,
"status": "fail",
"error": "Verification Failed"
},
{
"model": "Qwen/Qwen3-14B-AWQ",
"tp": 1,
"util": "0.90",
"max_seqs": 1,
"model_limit": 40960,
"configured_len": 40960,
"real_capacity": 655712,
"status": "success",
"error": "",
"max_context_1_user": 40960
},
{
"model": "Qwen/Qwen3-14B-AWQ",
"tp": 1,
"util": "0.90",
"max_seqs": 4,
"model_limit": 40960,
"configured_len": 40960,
"real_capacity": 655616,
"status": "success",
"error": "",
"max_context_1_user": 40960
},
{
"model": "Qwen/Qwen3-14B-AWQ",
"tp": 1,
"util": "0.90",
"max_seqs": 8,
"model_limit": 40960,
"configured_len": 40960,
"real_capacity": 655600,
"status": "success",
"error": "",
"max_context_1_user": 40960
},
{
"model": "Qwen/Qwen3-14B-AWQ",
"tp": 1,
"util": "0.90",
"max_seqs": 16,
"model_limit": 40960,
"configured_len": 40960,
"real_capacity": 655600,
"status": "success",
"error": "",
"max_context_1_user": 40960
},
{
"model": "openai/gpt-oss-20b",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 2232848,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-20b",
"tp": 1,
"util": "0.95",
"max_seqs": 4,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 2232560,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-20b",
"tp": 1,
"util": "0.95",
"max_seqs": 8,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 2232544,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-20b",
"tp": 1,
"util": "0.95",
"max_seqs": 16,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 2232544,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-120b",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 711360,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-120b",
"tp": 1,
"util": "0.95",
"max_seqs": 4,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 711168,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-120b",
"tp": 1,
"util": "0.95",
"max_seqs": 8,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 711168,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "openai/gpt-oss-120b",
"tp": 1,
"util": "0.95",
"max_seqs": 16,
"model_limit": 131072,
"configured_len": 131072,
"real_capacity": 711168,
"status": "success",
"error": "",
"max_context_1_user": 131072
},
{
"model": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 262144,
"configured_len": 262144,
"real_capacity": 1097712,
"status": "success",
"error": "",
"max_context_1_user": 262144
},
{
"model": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit",
"tp": 1,
"util": "0.95",
"max_seqs": 4,
"model_limit": 262144,
"configured_len": 0,
"real_capacity": 0,
"status": "fail",
"error": "Verification Failed"
},
{
"model": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit",
"tp": 1,
"util": "0.90",
"max_seqs": 4,
"model_limit": 262144,
"configured_len": 209715,
"real_capacity": 1029856,
"status": "success",
"error": "Process died or timed out",
"max_context_1_user": 209715
},
{
"model": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit",
"tp": 1,
"util": "0.90",
"max_seqs": 8,
"model_limit": 262144,
"configured_len": 0,
"real_capacity": 0,
"status": "fail",
"error": "Verification Failed"
},
{
"model": "dazipe/Qwen3-Next-80B-A3B-Instruct-GPTQ-Int4A16",
"tp": 1,
"util": "0.95",
"max_seqs": 1,
"model_limit": 262144,
"configured_len": 0,
"real_capacity": 0,
"status": "fail",
"error": "Verification Failed"
},
{
"model": "dazipe/Qwen3-Next-80B-A3B-Instruct-GPTQ-Int4A16",
"tp": 1,
"util": "0.90",
"max_seqs": 1,
"model_limit": 262144,
"configured_len": 262144,
"real_capacity": 696320,
"status": "success",
"error": "",
"max_context_1_user": 262144
},
{
"model": "dazipe/Qwen3-Next-80B-A3B-Instruct-GPTQ-Int4A16",
"tp": 1,
"util": "0.90",
"max_seqs": 4,
"model_limit": 262144,
"configured_len": 0,
"real_capacity": 0,
"status": "fail",
"error": "Verification Failed"
}
]
In neuem Issue referenzieren Git Blame ansehen Permalink kopieren